场景：
-
一段音频中有多个说话人，将不同的人说的话分离出来
-
已知一些人的语音特征，跟分离出来的片段，分别求特征的余弦距离，余弦距离最小的作为说话的人
安装：
pip install pyannote.audio# _*_ coding: utf-8 _*_
import torch
from pyannote.audio import Model, Pipeline, Inference
from pyannote.core import Segment
from scipy.spatial.distance import cosine
def extract_speaker_embedding(pipeline, audio_file, speaker_label):
diarization = pipeline(audio_file)
speaker_embedding = None
for turn, _, label in diarization.itertracks(yield_label=True):
if label == speaker_label:
segment = Segment(turn.start, turn.end)
speaker_embedding = inference.crop(audio_file, segment)
break
return speaker_embedding
# 对于给定的音频，提取声纹特征并与人库中的声纹进行比较
def recognize_speaker(pipeline, audio_file):
diarization =